Change search
ReferencesLink to record
Permanent link

Direct link
Monocular 3D reconstruction of human motion in long action sequences
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
2004 (English)In: COMPUTER VISION: ECCV 2004, PT 4, BERLIN: SPRINGER , 2004, Vol. 2034, 442-455 p.Conference paper (Refereed)
Abstract [en]

A novel algorithm is presented for the 3D reconstruction of human action in long (> 30 second) monocular image sequences. A sequence is represented by a small set of automatically found representative keyframes. The skeletal joint positions are manually located in each keyframe and mapped to all other frames in the sequence. For each keyframe a 3D key pose is created, and interpolation between these 3D body poses, together with the incorporation of limb length and symmetry constraints, provides a smooth initial approximation of the 3D motion. This is then fitted to the image data to generate a realistic 3D reconstruction. The degree of manual input required is controlled by the diversity of the sequence's content. Sports' footage is ideally suited to this approach as it frequently contains a limited number of repeated actions. Our method is demonstrated on a long (36 second) sequence of a woman playing tennis filmed with a non-stationary camera. This sequence required manual initialisation on < 1.5% of the frames, and demonstrates that the system can deal with very rapid motion, severe self-occlusions, motion blur and clutter occurring over several concurrent frames. The monocular 3D reconstruction is verified by synthesising a view from the perspective of a 'ground truth' reference camera, and the result is seen to provide a qualitatively accurate 3D reconstruction of the motion.

Place, publisher, year, edition, pages
BERLIN: SPRINGER , 2004. Vol. 2034, 442-455 p.
, Source: COMPUTER VISION - ECCV 2004, PT 4 Book Series:, ISSN 0302-9743 ; 2034
National Category
Computer and Information Science
URN: urn:nbn:se:kth:diva-43995ISI: 000221523800036ScopusID: 2-s2.0-35048873748ISBN: 3-540-21981-1OAI: diva2:449125
8th European Conference on Computer Vision. Prague, CZECH REPUBLIC. MAY 11-14, 2004
QC 20111019Available from: 2011-10-19 Created: 2011-10-19 Last updated: 2012-03-22Bibliographically approved

Open Access in DiVA

No full text


Search in DiVA

By author/editor
Loy, GarethEriksson, MartinSullivan, JosephineCarlsson, Stefan
By organisation
Numerical Analysis and Computer Science, NADAComputer Vision and Active Perception, CVAP
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 11 hits
ReferencesLink to record
Permanent link

Direct link